Ayaka Sakata

Profile Information

Affiliation

Associate Professor, Ochanomizu University

Team Director, AIP, RIKEN

Degree

Ph.D.(Mar, 2011, The University of Tokyo)

Contact information

ayakasakatais.ocha.ac.jp

Researcher number

80733071

J-GLOBAL ID

201501037290625048

researchmap Member ID

B000244765

Research Interests

• Statistical Physics
• Statistical Science
• Statistical Machine Learning
• Evolutional biology

Research Areas

• Natural sciences / Mathematical physics and basic theory / Statistical Physics
• Informatics / Soft computing / Information Processing

Research History

• Apr, 2025 - Present

  Team Director, AIP, RIKEN
• Apr, 2025 - Present

  Associate Professor, Ochanomizu University
• Apr, 2020 - Mar, 2025

  Associate Professor, The Institute of Statistical Mathematics
• Apr, 2015 - Mar, 2020

  Assistant Professor, The Institute of Statistical Mathematics
• Apr, 2014 - Mar, 2015

  Special PostDoctoral Researcher, RIKEN
• Apr, 2011 - Mar, 2014

  JSPS Research Fellow (PD), Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology
• Apr, 2008 - Mar, 2011

  JSPS Research Fellow (DC1), Graduate School of Arts and Sciences, The University of Tokyo

Committee Memberships

• 2024 - Present

  General Affairs Committee, The Japan Statistical Society
• 2021

  Japanese Journal of Statistics and Data Science編集委員
• Oct, 2016 - Sep, 2017

  日本物理学会 領域11運営委員

Awards

• Apr, 2019

  The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology, The Young Scientists’ Prize, Statistical Machine Learning based on spin-glass theory, Ministry of Education, Culture, Sports, Science and Technology

  Ayaka Sakata
• Nov, 2017

  IBIS2017 Presentation Award, Message Passing for nonconvex sparse penalties and its convergence condition

  Ayaka Sakata
• Jun, 2017

  Shiseido Female Researcher Science Grant
• Dec, 2014

  SITA Awards
• Nov, 2012

  IBIS2012 Poster Awards

Papers

• The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model

  Kaito Takanami, Takashi Takahashi, Ayaka Sakata

  NeurIPS2025 (The Thirty-Ninth Annual Conference on Neural Information Processing Systems), Dec, 2025 Peer-reviewedLast author
• Effect of Weight Quantization on Learning Models by Typical Case Analysis

  Shuhei Kashiwamura, Ayaka Sakata, Masaaki Imaizumi

  2024 IEEE International Symposium on Information Theory (ISIT), 357-362, Jul 7, 2024 Peer-reviewed
• Evolutionary Shaping of Low-Dimensional Path Facilitates Robust and Plastic Switching Between Phenotypes

  Ayaka Sakata, Kunihiko Kaneko

  Physical Review Research, 5(4) 043296, Dec 26, 2023 Peer-reviewedLead authorCorresponding author
• Decision Theoretic Cutoff and ROC Analysis for Bayesian Optimal Group Testing

  Ayaka Sakata, Yoshiyuki Kabashima

  IEEE Transactions on Information Theory, 69(9) 5902-5920, Sep, 2023 Peer-reviewedLead authorCorresponding author
• Prediction errors for penalized regressions based on generalized approximate message passing

  Ayaka Sakata

  Journal of Physics A: Mathematical and Theoretical, Jan, 2023 Peer-reviewedInvitedLead authorLast authorCorresponding author
• ベイズ的グループテストのカットオフ値評価とROC解析

  坂田綾香, 樺島祥介

  統計数理, 70(1) 89-114, 2022 Peer-reviewedInvitedLead authorCorresponding author
• Perfect reconstruction of sparse signals with piecewise continuous nonconvex penalties and nonconvexity control

  Ayaka Sakata, Tomoyuki Obuchi

  Journal of Statistical Mechanics: Theory and Experiment, 2021(9) 093401-093401, Sep, 2021 Peer-reviewedLead authorCorresponding author
• Active pooling design in group testing based on Bayesian posterior prediction

  Ayaka Sakata

  Physical Review E, 103(2) 022110, Feb 5, 2021 Peer-reviewedLead authorLast authorCorresponding author
• Bayesian Inference of Infected Patients in Group Testing with Prevalence Estimation

  Ayaka Sakata

  Journal of the Physical Society of Japan, 89(8) 084001-084001, Aug 15, 2020 Peer-reviewedLead authorLast authorCorresponding author
• Dimensional Reduction in Evolving Spin-Glass Model: Correlation of Phenotypic Responses to Environmental and Mutational Changes

  Ayaka Sakata, Kunihiko Kaneko

  Physical Review Letters, 124(21) 218101-1-218101-6, May 26, 2020 Peer-reviewedLead authorCorresponding author
• Cross validation in sparse linear regression with piecewise continuous nonconvex penalties and its acceleration

  Tomoyuki Obuchi, Ayaka Sakata

  Journal of Physics A: Mathematical and Theoretical, 52(41) 414003-1-414003-30, 2019 Peer-reviewedLast author
• Approximate message passing for nonconvex sparse regularization with stability and asymptotic analysis

  Ayaka Sakata, Yingying Xu

  Journal of Statistical Mechanics: Theory and Experiment, 2018(3) 033404-1-35, Mar 13, 2018 Peer-reviewedLead authorLast authorCorresponding author
• Estimator of Prediction Error Based on Approximate Message Passing for Penalized Linear Regression

  A. Sakata

  J. Stat. Mech., 2018 063404-1-24, 2018 Peer-reviewedLead authorLast authorCorresponding author
• Evaluation of generalized degrees of freedom for sparse estimation by replica method

  A. Sakata

  JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2016 123302-1-29, Dec, 2016 Peer-reviewedLead authorLast authorCorresponding author
• Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization

  Yoshiyuki Kabashima, Florent Krzakala, Marc Mezard, Ayaka Sakata, Lenka Zdeborova

  IEEE TRANSACTIONS ON INFORMATION THEORY, 62(7) 4228-4265, Jul, 2016 Peer-reviewed
• Replica Symmetric Bound for Restricted Isometry Constant

  Ayaka Sakata, Yoshiyuki Kabashima

  2015 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2015 2006-2010, 2015 Peer-reviewedLead authorCorresponding author
• Statistical mechanics of dictionary learning

  Ayaka Sakata, Yoshiyuki Kabashima

  EPL, 103(2) 28008, Jul, 2013 Peer-reviewedLead authorCorresponding author
• Time evolution of the autocorrelation function in dynamical replica theory

  A. Sakata

  JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 46(16) 165001, Apr, 2013 Peer-reviewedLead authorLast authorCorresponding author
• Sample Complexity of Bayesian Optimal Dictionary Learning

  Ayaka Sakata, Yoshiyuki Kabashima

  2013 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY PROCEEDINGS (ISIT), 2013 669-673, 2013 Peer-reviewedLead authorCorresponding author
• Replica symmetry breaking in an adiabatic spin-glass model of adaptive evolution

  Ayaka Sakata, Koji Hukushima, Kunihiko Kaneko

  EPL, 99(6) 68004, Sep, 2012 Peer-reviewedLead authorCorresponding author

Misc.

• 生物システムの頑健性と可塑性を支える進化的次元圧縮

  坂田綾香, 金子邦彦

  日本神経回路学会誌, 30(3), Sep, 2024 InvitedLead authorCorresponding author
• 非凸スパース制約最小化による信号復元:非凸性制御によるアルゴリズム軌道の安定化

  坂田綾香, 小渕智之

  日本統計学会和文誌, 53(1), Sep, 2023 Peer-reviewedInvitedLead authorCorresponding author
• ベイズ推定に基づく適応的グループテスト

  坂田綾香

  日本物理学会誌, (4), Apr, 2021 Peer-reviewedInvitedLead author
• レプリカ対称性/階層的地形の数学的表現

  坂田綾香

  数学セミナー, Dec, 2019 Invited
• レプリカ法による制限等長定数の評価

  坂田綾香, 樺島祥介

  情報理論とその応用シンポジウム予稿集(CD-ROM), 38th ROMBUNNO.1.4.4, Nov 17, 2015
• レプリカ法による制限等長定数の評価

  坂田綾香, 樺島祥介

  日本物理学会講演概要集(CD-ROM), 70(1) ROMBUNNO.24ABL-3, Mar 24, 2015
• 統計力学的アルゴリズムによる特徴空間のスパース表現

  坂田綾香, 樺島祥介

  情報理論とその応用シンポジウム予稿集(CD-ROM), 37th ROMBUNNO.2.3.3, Dec 2, 2014
• Statistical mechanics of Bayesian optimal dictionary learning

  SAKATA Ayaka, KABASHIMA Yoshiyuki

  電子情報通信学会技術研究報告. IBISML, 情報論的学習理論と機械学習, 113(286) 31-38, Nov 5, 2013
• Typical case analysis of sample complexity in Dictionary Learning

  SAKATA Ayaka, KABASHIMA Yoshiyuki

  112(279) 113-120, Oct 31, 2012

Presentations

• Objective perturbation型プライバシー LASSOにおける推定値の分布評価

  Ayaka Sakata, Haruka Tanzawa

  日本物理学会第80回年次大会, Sep 18, 2025
• Objective perturbation型プライバシー LASSOの高次元における典型性能評価

  Ayaka Sakata, Haruka Tanzawa

  Sep 10, 2025
• Nonconvexity annealing under 1-step replica symmetry breaking

  Ayaka Sakata, Tomoyuki Obuchi

  Learning and Optimization in High Dimensions (StatPhys29 Satellite Workshop), Jul 9, 2025
• 近似確率伝搬法から考える汎化誤差

  坂田綾香

  AI・データ利活用研究会, Mar 21, 2025 Invited
• 1段階レプリカ対称性の破れを利用した非凸性アニーリング

  坂田綾香, 小渕智之

  日本物理学会2025年春季大会, Mar 18, 2025
• Understanding Generalization in Statistical Models: Insights from Statistical Physics

  Ayaka Sakata

  Computational and Physical Understanding of Biological Information Processing, Mar 12, 2025 Invited
• 低次元描像に基づく複数表現型の安定的発現と状態遷移

  坂田綾香

  ネットワーク科学研究会2024, Mar 4, 2025 Invited
• Evolutional Construction of Stable Expression and Switching Paths for Multiple Phenotypes

  Ayaka Sakata, Kunihiko Kaneko

  1st India-Japan Workshop on Physical Aspects of Living Systems, Feb 20, 2025 Invited
• 非凸正則化のアニーリングを用いたスパース信号復元

  坂田綾香, 小渕智之

  情報計測オンラインセミナー, Feb 15, 2025 Invited
• Controlling algorithm trajectory through free energy landscapes: overcoming difficulties in nonconvex sparse penalties

  Ayaka Sakata, Tomoyuki Obuchi

  IASC-ARS interim conference, Dec 13, 2024 Invited
• 1段階レプリカ対称性の破れを考慮した非凸性アニーリング

  坂田綾香, 小渕智之

  IBIS2024, Nov, 2024
• 自由エネルギー地形から理解する確率的推論

  坂田綾香

  日本物理学会第79回年次大会 領域3、11、12合同シンポジウム「データ科学を活用した自由エネルギー解析:物質構造と材料機能の接続に向けて」, Sep 18, 2024 Invited
• Approximate Inference in Query Learning

  Ayaka Sakata

  RIMS Symposium "Modeling and Learning of Stochastic Dynamics", Jul 10, 2024 Invited
• Query by Committeeの性能解析とアルゴリズム

  坂田綾香, 樺島祥介

  情報統計力学とその周辺 ミニ研究集会, Apr, 2024 Invited
• 進化的次元圧縮がもたらす表現型の頑健性と可塑性の両立

  坂田綾香

  国立精神・神経医療研究センター,脳病態数理・データ科学セミナーシリーズ, Feb 27, 2024 Invited
• グループテストにおける推論と最適カットオフ評価

  坂田綾香

  東北大学青葉山統計科学セミナー, Feb 8, 2024 Invited
• 非凸スパース制約最小化による信号復元

  坂田綾香

  京都大学数理解析研究所セミナー, Jan 23, 2024 Invited
• Evolutionary Shaping of Low-Dimensional Path Facilitates Robust and Plastic Switching Between Phenotypes

  坂田綾香, 金子邦彦

  定量生物学の会第十一回年会, Jan, 2024
• グラフィカルモデルを用いた確率推論の回帰問題における展開

  坂田綾香

  東京大学駒場物性セミナー, Dec, 2023 Invited
• グラフィカルモデルを用いた確率推論の回帰問題における展開

  Ayaka Sakata

  Sep 22, 2023 Invited

Teaching Experience

• Sep, 2025 - Sep, 2025

  データ科学特論I (The University of Osaka)
• Apr, 2024 - Jul, 2024

  Statistical Physics for Random Systems (The Graduate University for Advanced Studies)
• Nov, 2023 - Dec, 2023

  相関基礎科学特殊講義VI (東京大学 大学院総合文化研究科)
• Dec, 2022 - Feb, 2023

  数理計算科学特論A (東京工業大学 情報理工学院)
• 2023

  計算推論基礎 (The Graduate University for Advanced Studies)
• Sep, 2022

  リーディングDAT無料講座LX (統計数理研究所)
• 2021

  計算推論基礎 (総合研究大学院大学 複合科学研究科 統計科学専攻)
• 2021

  リーディングDAT A (統計数理研究所)
• 2018 - 2019

  情報リテラシー (首都大学東京)
• 2019

  リーディングDAT講座「データサイエンスの基礎」 (統計数理研究所)

Professional Memberships

• THE JAPAN STATISTICAL SOCIETY
• THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
• THE PHYSICAL SOCIETY OF JAPAN

Research Projects

• 確率的推論によるデータ取得とデータ解析の包括的最適化

  さきがけ「計測・解析プロセス革新のための基盤の構築」, 科学技術振興機構, Oct, 2023 - Mar, 2027
• Statistical mechanics approach to high-dimensional machine learning

  Grants-in-Aid for Scientific Research Grant-in-Aid for Transformative Research Areas (A), Grant-in-Aid for Transformative Research Areas (A), Japan Society for the Promotion of Science, Jun, 2022 - Mar, 2027
• 大自由度生命システムの次元縮減:検証、理論化、生物状態論及び神経系学習への展開

  科学研究費助成事業 基盤研究(A), 基盤研究(A), 日本学術振興会, Apr, 2020 - Mar, 2024

  金子 邦彦
• 求解軌道のマクロ表現によるアルゴリズム制御理論の創出

  さきがけ, 科学技術振興機構, Oct, 2019 - Mar, 2023

  坂田綾香
• 階層モデルにおけるベイズ的スパース推定に対するモデル選択理論の構成

  科学研究費補助金(若手研究), 文部科学省, Apr, 2019 - Mar, 2022

  坂田綾香
• ベイズ推定に基づく適応的グループテストのアルゴリズム開発:検体検査の効率化と誤り訂正

  研究助成, カシオ科学振興財団, Dec, 2020 - Nov, 2021

  坂田綾香
• 非凸スパース正則化の統計力学による解析

  科学研究費補助金(若手研究B), 文部科学省, Apr, 2016 - Mar, 2019

  坂田綾香
• Statistical mechanics approach to massive sparse modeling

  Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area), Japan Society for the Promotion of Science, Jun, 2013 - Mar, 2018

  KABASHIMA Yoshiyuki, OBUCHI Tomoyuki
• Statistical mechanics of linear and non-linear matrix factorization and a theoretical analysis of auto encoder

  Grants-in-Aid for Scientific Research, Grant-in-Aid for Research Activity Start-up, Japan Society for the Promotion of Science, Oct, 2014 - Mar, 2016

  Sakata Ayaka
• Partial annealingによるブラインド圧縮センシングの統計力学的解析

  特別研究員奨励費, 特別研究員奨励費, 日本学術振興会, Apr, 2011 - Mar, 2014

  坂田綾香
• スピンモデルによる適応的進化の統計力学的研究

  特別研究員奨励費, 特別研究員奨励費, 日本学術振興会, Apr, 2008 - Mar, 2011

  坂田綾香

Academic Activities

• ism_statphys

  Planning, management, etc., Panel moderator, session chair, etc.

  伊庭幸人; 坂田綾香; 菊地和平, 2020 - Present

Social Activities

• 兵庫高校「東京未来フロンティアツアー」講師

  Lecturer

Media Coverage

• Environmental noise changes evolutionary cooperation between cellular components, model shows

  AAAS, EurekAlert!, Jun 6, 2020 Internet
• Mathematical theory for biological evolution using statistical physics

  The Science News Ltd., The Science News, Jun, 2020 Newspaper, magazine
• Limits on evolution revealed by statistical physics

  May 29, 2020 Internet